#include <linux/init_task.h>
#include <linux/perf_event.h>
#include <trace/events/sched.h>
+#include <linux/hw_breakpoint.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
detach_pid(p, PIDTYPE_SID);
list_del_rcu(&p->tasks);
+ list_del_init(&p->sibling);
__get_cpu_var(process_counts)--;
}
list_del_rcu(&p->thread_group);
- list_del_init(&p->sibling);
}
/*
BUG_ON(!sig);
BUG_ON(!atomic_read(&sig->count));
- sighand = rcu_dereference(tsk->sighand);
+ sighand = rcu_dereference_check(tsk->sighand,
+ rcu_read_lock_held() ||
+ lockdep_tasklist_lock_is_held());
spin_lock(&sighand->siglock);
posix_cpu_timers_exit(tsk);
* We won't ever get here for the group leader, since it
* will have been the last reference on the signal_struct.
*/
- sig->utime = cputime_add(sig->utime, task_utime(tsk));
- sig->stime = cputime_add(sig->stime, task_stime(tsk));
- sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
+ sig->utime = cputime_add(sig->utime, tsk->utime);
+ sig->stime = cputime_add(sig->stime, tsk->stime);
+ sig->gtime = cputime_add(sig->gtime, tsk->gtime);
sig->min_flt += tsk->min_flt;
sig->maj_flt += tsk->maj_flt;
sig->nvcsw += tsk->nvcsw;
repeat:
tracehook_prepare_release_task(p);
/* don't need to get the RCU readlock here - the process is dead and
- * can't be modifying its own credentials */
+ * can't be modifying its own credentials. But shut RCU-lockdep up */
+ rcu_read_lock();
atomic_dec(&__task_cred(p)->user->processes);
+ rcu_read_unlock();
proc_flush_task(p);
/*
* It is safe to dereference the fd table without RCU or
* ->file_lock because this is the last reference to the
- * files structure.
+ * files structure. But use RCU to shut RCU-lockdep up.
*/
+ rcu_read_lock();
fdt = files_fdtable(files);
+ rcu_read_unlock();
for (;;) {
unsigned long set;
i = j * __NFDBITS;
* at the end of the RCU grace period. Otherwise,
* you can free files immediately.
*/
+ rcu_read_lock();
fdt = files_fdtable(files);
if (fdt != &files->fdtab)
kmem_cache_free(files_cachep, files);
free_fdtable(fdt);
+ rcu_read_unlock();
}
}
/*
* Any that need to be release_task'd are put on the @dead list.
*/
-static void reparent_thread(struct task_struct *father, struct task_struct *p,
+static void reparent_leader(struct task_struct *father, struct task_struct *p,
struct list_head *dead)
{
- if (p->pdeath_signal)
- group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);
-
list_move_tail(&p->sibling, &p->real_parent->children);
if (task_detached(p))
reaper = find_new_reaper(father);
list_for_each_entry_safe(p, n, &father->children, sibling) {
- p->real_parent = reaper;
- if (p->parent == father) {
- BUG_ON(task_ptrace(p));
- p->parent = p->real_parent;
- }
- reparent_thread(father, p, &dead_children);
+ struct task_struct *t = p;
+ do {
+ t->real_parent = reaper;
+ if (t->parent == father) {
+ BUG_ON(task_ptrace(t));
+ t->parent = t->real_parent;
+ }
+ if (t->pdeath_signal)
+ group_send_sig_info(t->pdeath_signal,
+ SEND_SIG_NOINFO, t);
+ } while_each_thread(p, t);
+ reparent_leader(father, p, &dead_children);
}
write_unlock_irq(&tasklist_lock);
* an exiting task cleaning up the robust pi futexes.
*/
smp_mb();
- spin_unlock_wait(&tsk->pi_lock);
+ raw_spin_unlock_wait(&tsk->pi_lock);
if (unlikely(in_atomic()))
printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
preempt_count());
acct_update_integrals(tsk);
-
+ /* sync mm's RSS info before statistics gathering */
+ if (tsk->mm)
+ sync_mm_rss(tsk, tsk->mm);
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
hrtimer_cancel(&tsk->signal->real_timer);
exit_itimers(tsk->signal);
+ if (tsk->mm)
+ setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
}
acct_collect(code, group_dead);
if (group_dead)
exit_thread();
cgroup_exit(tsk, 1);
- if (group_dead && tsk->signal->leader)
+ if (group_dead)
disassociate_ctty(1);
module_put(task_thread_info(tsk)->exec_domain->module);
- if (tsk->binfmt)
- module_put(tsk->binfmt->module);
proc_exit_connector(tsk);
/*
+ * FIXME: do that only when needed, using sched_exit tracepoint
+ */
+ flush_ptrace_hw_breakpoint(tsk);
+ /*
* Flush inherited counters to the parent - before the parent
* gets woken up by child-exit notifications.
*/
tsk->mempolicy = NULL;
#endif
#ifdef CONFIG_FUTEX
- if (unlikely(!list_empty(&tsk->pi_state_list)))
- exit_pi_state_list(tsk);
if (unlikely(current->pi_state_cache))
kfree(current->pi_state_cache);
#endif
tsk->flags |= PF_EXITPIDONE;
if (tsk->io_context)
- exit_io_context();
+ exit_io_context(tsk);
if (tsk->splice_pipe)
__free_pipe_info(tsk->splice_pipe);
int __user *wo_stat;
struct rusage __user *wo_rusage;
+ wait_queue_t child_wait;
int notask_error;
};
-static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
+static inline
+struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
{
- struct pid *pid = NULL;
- if (type == PIDTYPE_PID)
- pid = task->pids[type].pid;
- else if (type < PIDTYPE_MAX)
- pid = task->group_leader->pids[type].pid;
- return pid;
+ if (type != PIDTYPE_PID)
+ task = task->group_leader;
+ return task->pids[type].pid;
}
-static int eligible_child(struct wait_opts *wo, struct task_struct *p)
+static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
{
- int err;
-
- if (wo->wo_type < PIDTYPE_MAX) {
- if (task_pid_type(p, wo->wo_type) != wo->wo_pid)
- return 0;
- }
+ return wo->wo_type == PIDTYPE_MAX ||
+ task_pid_type(p, wo->wo_type) == wo->wo_pid;
+}
+static int eligible_child(struct wait_opts *wo, struct task_struct *p)
+{
+ if (!eligible_pid(wo, p))
+ return 0;
/* Wait for all children (clone and not) if __WALL is set;
* otherwise, wait for clone children *only* if __WCLONE is
* set; otherwise, wait for non-clone children *only*. (Note:
&& !(wo->wo_flags & __WALL))
return 0;
- err = security_task_wait(p);
- if (err)
- return err;
-
return 1;
}
put_task_struct(p);
infop = wo->wo_info;
- if (!retval)
- retval = put_user(SIGCHLD, &infop->si_signo);
- if (!retval)
- retval = put_user(0, &infop->si_errno);
- if (!retval)
- retval = put_user((short)why, &infop->si_code);
- if (!retval)
- retval = put_user(pid, &infop->si_pid);
- if (!retval)
- retval = put_user(uid, &infop->si_uid);
- if (!retval)
- retval = put_user(status, &infop->si_status);
+ if (infop) {
+ if (!retval)
+ retval = put_user(SIGCHLD, &infop->si_signo);
+ if (!retval)
+ retval = put_user(0, &infop->si_errno);
+ if (!retval)
+ retval = put_user((short)why, &infop->si_code);
+ if (!retval)
+ retval = put_user(pid, &infop->si_pid);
+ if (!retval)
+ retval = put_user(uid, &infop->si_uid);
+ if (!retval)
+ retval = put_user(status, &infop->si_status);
+ }
if (!retval)
retval = pid;
return retval;
if (unlikely(wo->wo_flags & WNOWAIT)) {
int exit_code = p->exit_code;
- int why, status;
+ int why;
get_task_struct(p);
read_unlock(&tasklist_lock);
if (likely(!traced) && likely(!task_detached(p))) {
struct signal_struct *psig;
struct signal_struct *sig;
+ unsigned long maxrss;
+ cputime_t tgutime, tgstime;
/*
* The resource counters for the group leader are in its
* need to protect the access to parent->signal fields,
* as other threads in the parent group can be right
* here reaping other children at the same time.
+ *
+ * We use thread_group_times() to get times for the thread
+ * group, which consolidates times for all threads in the
+ * group including the group leader.
*/
+ thread_group_times(p, &tgutime, &tgstime);
spin_lock_irq(&p->real_parent->sighand->siglock);
psig = p->real_parent->signal;
sig = p->signal;
psig->cutime =
cputime_add(psig->cutime,
- cputime_add(p->utime,
- cputime_add(sig->utime,
- sig->cutime)));
+ cputime_add(tgutime,
+ sig->cutime));
psig->cstime =
cputime_add(psig->cstime,
- cputime_add(p->stime,
- cputime_add(sig->stime,
- sig->cstime)));
+ cputime_add(tgstime,
+ sig->cstime));
psig->cgtime =
cputime_add(psig->cgtime,
cputime_add(p->gtime,
psig->coublock +=
task_io_get_oublock(p) +
sig->oublock + sig->coublock;
+ maxrss = max(sig->maxrss, sig->cmaxrss);
+ if (psig->cmaxrss < maxrss)
+ psig->cmaxrss = maxrss;
task_io_accounting_add(&psig->ioac, &p->ioac);
task_io_accounting_add(&psig->ioac, &sig->ioac);
spin_unlock_irq(&p->real_parent->sighand->siglock);
* then ->notask_error is 0 if @p is an eligible child,
* or another error from security_task_wait(), or still -ECHILD.
*/
-static int wait_consider_task(struct wait_opts *wo, struct task_struct *parent,
- int ptrace, struct task_struct *p)
+static int wait_consider_task(struct wait_opts *wo, int ptrace,
+ struct task_struct *p)
{
int ret = eligible_child(wo, p);
if (!ret)
return ret;
+ ret = security_task_wait(p);
if (unlikely(ret < 0)) {
/*
* If we have not yet seen any eligible child,
struct task_struct *p;
list_for_each_entry(p, &tsk->children, sibling) {
- /*
- * Do not consider detached threads.
- */
- if (!task_detached(p)) {
- int ret = wait_consider_task(wo, tsk, 0, p);
- if (ret)
- return ret;
- }
+ int ret = wait_consider_task(wo, 0, p);
+ if (ret)
+ return ret;
}
return 0;
struct task_struct *p;
list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
- int ret = wait_consider_task(wo, tsk, 1, p);
+ int ret = wait_consider_task(wo, 1, p);
if (ret)
return ret;
}
return 0;
}
+static int child_wait_callback(wait_queue_t *wait, unsigned mode,
+ int sync, void *key)
+{
+ struct wait_opts *wo = container_of(wait, struct wait_opts,
+ child_wait);
+ struct task_struct *p = key;
+
+ if (!eligible_pid(wo, p))
+ return 0;
+
+ if ((wo->wo_flags & __WNOTHREAD) && wait->private != p->parent)
+ return 0;
+
+ return default_wake_function(wait, mode, sync, key);
+}
+
+void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
+{
+ __wake_up_sync_key(&parent->signal->wait_chldexit,
+ TASK_INTERRUPTIBLE, 1, p);
+}
+
static long do_wait(struct wait_opts *wo)
{
- DECLARE_WAITQUEUE(wait, current);
struct task_struct *tsk;
int retval;
trace_sched_process_wait(wo->wo_pid);
- add_wait_queue(¤t->signal->wait_chldexit,&wait);
+ init_waitqueue_func_entry(&wo->child_wait, child_wait_callback);
+ wo->child_wait.private = current;
+ add_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait);
repeat:
/*
* If there is nothing that can match our critiera just get out.
}
end:
__set_current_state(TASK_RUNNING);
- remove_wait_queue(¤t->signal->wait_chldexit,&wait);
- if (wo->wo_info) {
- struct siginfo __user *infop = wo->wo_info;
-
- if (retval > 0)
- retval = 0;
- else {
- /*
- * For a WNOHANG return, clear out all the fields
- * we would set so the user can easily tell the
- * difference.
- */
- if (!retval)
- retval = put_user(0, &infop->si_signo);
- if (!retval)
- retval = put_user(0, &infop->si_errno);
- if (!retval)
- retval = put_user(0, &infop->si_code);
- if (!retval)
- retval = put_user(0, &infop->si_pid);
- if (!retval)
- retval = put_user(0, &infop->si_uid);
- if (!retval)
- retval = put_user(0, &infop->si_status);
- }
- }
+ remove_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait);
return retval;
}
wo.wo_stat = NULL;
wo.wo_rusage = ru;
ret = do_wait(&wo);
+
+ if (ret > 0) {
+ ret = 0;
+ } else if (infop) {
+ /*
+ * For a WNOHANG return, clear out all the fields
+ * we would set so the user can easily tell the
+ * difference.
+ */
+ if (!ret)
+ ret = put_user(0, &infop->si_signo);
+ if (!ret)
+ ret = put_user(0, &infop->si_errno);
+ if (!ret)
+ ret = put_user(0, &infop->si_code);
+ if (!ret)
+ ret = put_user(0, &infop->si_pid);
+ if (!ret)
+ ret = put_user(0, &infop->si_uid);
+ if (!ret)
+ ret = put_user(0, &infop->si_status);
+ }
+
put_pid(pid);
/* avoid REGPARM breakage on x86: */